Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/jbdamask/mcbrain/mcbrain-setupgit clone --depth 1 https://github.com/jbdamask/McBrainWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00033 | $0.00519 |
| Opus 5 | $0.00016 | $0.00260 |
| Sonnet 5 | $0.00007 | $0.00104 |
| Haiku 4.5 | $0.00003 | $0.00052 |
Grade A, and why
mcbrain-setup scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/mcbrain-setup
Provision a new McBrain vault by running the mcbrain-setup SKILL
end-to-end.
This is NOT a plugin-builder invocation
The McBrain plugin is already built and shipped. This command provisions a new vault using the existing plugin. Do not render an intake card with project-type selectors ("Home maintenance", "Renovation & projects", etc.). Do not ask "What will this McBrain be for?". Do not ask "Which skills/commands would you like included?". Those are plugin-builder behaviors and they don't apply here.
Use the SKILL's prescribed AskUserQuestion shapes for multi-choice
intake (OS, backup strategy, gh installed) and plain
conversational asks for free-text inputs (vault name, path, GitHub
username, version paste-backs). The full intake list is in the SKILL's
"Required intake" section — follow it verbatim, don't add questions.
Pre-filled argument
The user provided: $ARGUMENTS
If $ARGUMENTS is non-empty, treat it as the user's chosen McBrain
name and derive MCP_NAME from it:
- If it already starts with
mcbrain-, use it as-is (e.g.mcbrain-house→mcbrain-house). - Otherwise prefix it (
finance→mcbrain-finance,AI Science→mcbrain-ai-science).
This skips Step 1's name question. Confirm the derived MCP_NAME with
the user in one short sentence, then continue to Step 2 (backup strategy)
without re-asking the name. If the user wants to change it, accept
the change and move on.
If $ARGUMENTS is empty, run Step 1 normally (ask for the name).
Run the SKILL
Invoke the mcbrain-setup SKILL and follow it from Step 0 (or Step 1
if $ARGUMENTS filled the name) through Step 10. Don't paraphrase the
SKILL's prescribed AskUserQuestion payloads — use them verbatim.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 49 lines · 33 tokens per session scan A 173497ff452b
mcbrain-setup is a command published in the GitHub repository jbdamask/McBrain (2 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 519 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.